AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 231
Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences
Proactive human-robot collaboration requires autonomous systems to infer not only immediate actions but also the underlying hierarchical intentions governing human behavior.Reinforcement Learning for Large-Scale Lifelong Multi-Agent Path Finding with Shared Spatial Fields
Large-scale applications of lifelong multi-agent path finding (LMAPF) call for computationally inexpensive movement decisions under changing traffic conditions and across varied layouts.Link Both Views: Cross-Image Routing Attention for Dual-Endpoint V2I Beam-Pair Power Prediction
For sensing-aided communications, single-endpoint sensing offers only a partial view of propagation, motivating link-centric sensing across both endpoints.Hierarchical Time Series Forecasting with Operator-Valued Kernels
Hierarchical time series forecasting requires generating accurate predictions that are coherent across multiple levels of aggregation.A Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs
Parallel generation is widely regarded as an inherent advantage of diffusion large language models.Operator Surrogates
This chapter provides a mathematical introduction to operator surrogates, which are finite-parametric maps approximating complex (typically nonlinear) operators between infinite-dimensional…A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization
Domain-specific curvature is an appealing idea for domain generalization (DG), but curvature learning can denote substantially different computations.When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability
Deep reinforcement learning agents in partially observable competitive games must act on beliefs about an unseen opponent's intent.LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and…Teach Me After You Learn It: Lookahead Self-Distillation for RLVR
On-policy self-distillation (OPSD) has emerged as a popular training paradigm for LLMs, providing dense, token-level supervision by aligning a model's own distribution with the distribution induced…Optimal Online Regret for Context-Lumpable Bandits
We study stochastic contextual bandits with an unknown context-lumpable structure.PING: physics informed graph neural network for advection-diffusion processes with applications to solar power forecasting
Advection-diffusion plays an essential role in transport phenomena such as atmospheric and cloud dynamics.Reliable Risk Estimation with Kernel Mean Matching under Dependent Sampling
Kernel Mean Matching (KMM) estimates risk under covariate shift by reweighting labelled source samples so that their kernel mean embedding matches that of unlabeled target samples.Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller
Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent training.Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomalies
Detectors of logical anomalies, such as missing, extra or wrongly combined parts, usually score a test image by its distance from normal (good) images.Bayesian Optimization of CVaR with Unknown Hyperparameters
We study Bayesian optimization of the Conditional Value-at-Risk (CVaR) of an expensive black-box function that depends on a decision and an environmental variable.Over-parameterization Is Neither Robust nor Fragile in Matrix Sensing: A Geometric Theory of Solution Robustness
Over-parameterization is ubiquitous in modern machine learning, yet its effect on robustness remains poorly understood.Probing the Geometry of Color Representations in Multilingual Language Models
Do multilingual language models learn a universal internal geometry for color, and is it perceptually grounded or primarily linguistic?On the Optimality of Random Features under General Conditions: Misspecified Cases and Robust Learning
Random features provide a standard approach to scaling kernel methods to large datasets by approximating the kernel with a finite-dimensional feature map.Beyond Task Success: A Theory of Representation Reuse
A learned representation is useful beyond its source task only if later tasks can make use of what the encoder has already learned.